CN103226827A - Camera external parameter correction method and device, and assistant parking system - Google Patents
Camera external parameter correction method and device, and assistant parking system Download PDFInfo
- Publication number
- CN103226827A CN103226827A CN2013100922993A CN201310092299A CN103226827A CN 103226827 A CN103226827 A CN 103226827A CN 2013100922993 A CN2013100922993 A CN 2013100922993A CN 201310092299 A CN201310092299 A CN 201310092299A CN 103226827 A CN103226827 A CN 103226827A
- Authority
- CN
- China
- Prior art keywords
- parameter
- fitted
- template
- camera
- picture
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a camera external parameter correction method and device, and an assistant parking system, and adopts the structure that a debugging template is placed in an area in which at least two cameras can detect, wherein part of cameras are provided with reliable external parameters; a certain camera needs to perform external parameters correction; template images corresponding to the same debugging template are obtained from the source images shot by the cameras, and are matched so as to obtain at least two matching images; parameter errors of the matching images relevant to the external parameters of the cameras is determined according to size parameters of the matching images; the external parameters of one camera is corrected based on the parameter errors. In this way, camera external parameter adjustment can be conducted by the method as long as the debugging template is unfolded and placed in the area where the cameras can detect and cameras with reliable external parameters are provided. The camera external parameter correction method simplifies the laying condition of the debugging template, so that external parameter correction efficiency of the cameras is further improved.
Description
Technical field
The application relates to the camera technique field, relates in particular to the bearing calibration of a kind of camera external parameter, device and auxiliary parking system.
Background technology
Along with the continuous increase of automobile quantity, the road environment that day by day blocks up brings increasing inconvenience to the driver.The driver can be subjected to the restriction of objective condition such as the visual field and parking stall be narrow and small when parking, very easily take place to wipe to bump accident, and then bring unnecessary loss.At present, in the various auxiliary parking systems, visual panorama auxiliary parking system can provide real-time overhead view image around the vehicle body, and its panoramic picture that provides eliminated the blind area around the vehicle body, can park to the driver and provide effectively auxiliary.
The panorama auxiliary parking system that uses on the automobile is general to adopt a plurality of wide-angle imaging heads, and is separately positioned on around the vehicle body, gathers the vehicle body interior image of certain limit on every side respectively.System to each camera collection to image handle, and be spliced into the general view in a width of cloth car week.Because camera has certain alignment error when mounted, cause splicing general view, therefore, need when installing, proofread and correct the external parameter of camera.
The prior camera external parameter is proofreaied and correct the strict world coordinate system that makes up based on the vehicle body geometrical boundary that depends on, world coordinate system comprises with a certain end points of vehicle body as initial point, establish orthogonal x axle based on the right-handed helix rule, y axle and z axle, the camera external parameter is corresponding with world coordinate system, it mainly comprises x axle rotation parameter, y axle rotation parameter, z axle rotation parameter, x axle translation parameters, y axle translation parameters and z axle translation parameters etc., and the debugging template needs strict geometrical boundary large tracts of land according to vehicle body to lay, as shown in Figure 1, the debugging template generally adopts the alternate rectangular cloth 101 of 2-4 piece different size black and white grid, the limit of rectangular cloth 101 need with the vehicle body boundary alignment (as rectangle selvedge a among Fig. 1 and vehicle body border b, shown in rectangle selvedge c and the vehicle body border d etc.), internal system stores the standard picture corresponding with rectangular cloth 101, system extracts after the template image from the source images that camera is taken, standard picture and template image can be compared, adjust the external parameter of camera according to contrast gained image difference, make the template image and the standard picture of final acquisition approximate, and then finish the camera external parameter and proofread and correct.But, because the construction conditions of debugging template is strict, carrying out auxiliary parking system camera external parameter timing, need be to stopping all strict laying of debugging template of each good car, greatly reduced the efficient that the camera external parameter is proofreaied and correct, especially when auxiliary parking system was installed in enormous quantities, therefore installation effectiveness can be subjected to restricting significantly.
Summary of the invention
The application provides the bearing calibration of a kind of camera external parameter, device and auxiliary parking system, to simplify the construction conditions of debugging template, improves the camera external parameter and proofreaies and correct efficient.
According to the application's first aspect, the application provides the bearing calibration of a kind of camera external parameter, comprising:
Acquisition has first source images and second source images that second camera that first camera of reliable external parameter and pending external parameter proofread and correct is taken respectively the debugging template of launching;
From described first source images, obtain first template image of debugging template correspondence, from described second source images, obtain second template image of debugging template correspondence;
Respectively first template image and second template image are carried out match, obtain the first fitted figure picture and the second fitted figure picture with the similar fitted shapes of described debugging shape of template;
Obtain the first packet size parameter and the second packet size parameter of the described first fitted figure picture and the second fitted figure picture respectively;
By the described first packet size parameter and the second packet size parameter determine the parameter error relevant with the external parameter of second camera with;
External parameter with described parameter error and correction second camera.
According to the application's second aspect, the application provides the bearing calibration of a kind of camera external parameter, comprising:
Second source images that first source images that first camera that acquisition has a reliable external parameter is taken the first debugging template of launching, second camera that pending external parameter is proofreaied and correct are taken the described first debugging template launched and the second debugging template identical with the first debugging template, and have three source images of the 3rd camera of reliable external parameter to the described second debugging template shooting;
From described first source images, obtain first template image of the first debugging template correspondence, from described second source images, obtain second template image of the first debugging template correspondence and the 3rd template image of the second debugging template correspondence, from described the 3rd source images, obtain the 4th template image of the second debugging template correspondence;
Respectively first template image, second template image, the 3rd template image and the 4th template image are carried out match, obtain the first fitted figure picture, the second fitted figure picture, the 3rd fitted figure picture and the 4th fitted figure picture with the similar fitted shapes of the described first debugging shape of template;
Obtain the first packet size parameter, the second packet size parameter, the 3rd packet size parameter and the 4th packet size parameter of the described first fitted figure picture, the second fitted figure picture, the 3rd fitted figure picture and the 4th fitted figure picture respectively;
By the described first packet size parameter, the second packet size parameter, the 3rd packet size parameter and the 4th packet size parameter determine the parameter error relevant with the external parameter of second camera and;
External parameter with described parameter error and correction second camera.
According to the application's the third aspect, the application provides a kind of camera external parameter means for correcting, comprising:
Image collection module is used to obtain to have first camera of reliable external parameter and second camera of pending external parameter correction is debugged first source images and second source images that template is taken respectively to first of expansion;
The template image retrieval module is used for obtaining to debug first template image of template correspondence from described first source images, obtains second template image of debugging template correspondence from described second source images;
Fitting module is used for obtaining the first fitted figure picture and the second fitted figure picture respectively first template image and second template image are carried out match with the similar fitted shapes of described debugging shape of template;
Parameter calculating module is used for obtaining respectively the first packet size parameter and the second packet size parameter of the described first fitted figure picture and the second fitted figure picture;
Error calculating module, be used for by the described first packet size parameter and the second packet size parameter determine the parameter error relevant with the external parameter of second camera with;
Correction module is used for the external parameter with parameter error and correction second camera.
According to the application's fourth aspect, the application provides a kind of camera external parameter means for correcting, comprising:
Image collection module, be used to have second source images that first source images that first camera of reliable external parameter takes the first debugging template of launching, second camera that pending external parameter is proofreaied and correct are taken the described first debugging template launched and the second debugging template identical with the first debugging template, and have three source images of the 3rd camera of reliable external parameter the described second debugging template shooting;
The template image retrieval module, be used for obtaining first template image of the first debugging template correspondence from described first source images, from described second source images, obtain second template image of the first debugging template correspondence and the 3rd template image of the second debugging template correspondence, from described the 3rd source images, obtain the 4th template image of the second debugging template correspondence;
Fitting module, be used for obtaining the first fitted figure picture, the second fitted figure picture, the 3rd fitted figure picture and the 4th fitted figure picture respectively first template image, second template image, the 3rd template image and the 4th template image are carried out match with the similar fitted shapes of the described first debugging shape of template;
Parameter calculating module is used for obtaining respectively the first packet size parameter, the second packet size parameter, the 3rd packet size parameter and the 4th packet size parameter of the described first fitted figure picture, the second fitted figure picture, the 3rd fitted figure picture and the 4th fitted figure picture;
Error calculating module, be used for by the described first packet size parameter, the second packet size parameter, the 3rd packet size parameter and the 4th packet size parameter determine the parameter error relevant with the external parameter of second camera and;
Correction module is used for the external parameter with described parameter error and correction second camera.
According to the application's the 5th aspect, the application provides a kind of auxiliary parking system, comprises at least two cameras, and described system also comprises:
As above-mentioned camera external parameter means for correcting, and,
Output unit is used for described second camera being carried out after external parameter proofreaies and correct, and the final image that each camera is taken splices and exports.
The application's beneficial effect is:
By the bearing calibration of a kind of camera external parameter is provided, device and auxiliary parking system, the zone that template places at least two cameras all can detect will be debugged, wherein the part camera has reliable external parameter, a certain camera need carry out external parameter and proofread and correct, from the source images that each camera is taken, obtain the template image of same debugging template correspondence, and it is carried out match, obtain at least two fitted figure pictures, dimensional parameters according to each fitted figure picture, determine the parameter error of the fitted figure picture relevant with the camera external parameter, and proofread and correct the external parameter of above-mentioned a certain camera with parameter error, like this, only need make the debugging template launch to place the observable zone of camera, and setting has the camera of reliable external parameter, just can adopt said method to carry out the adjustment of camera external parameter, simplified the construction conditions of debugging template, and then improved the camera external parameter and proofreaied and correct efficient, when carrying out auxiliary parking system when installing in enormous quantities, only need to launch placement and debug template in the precalculated position, vehicle only needs to reach assigned address in the pipelining mode, can carry out the camera external parameter and proofread and correct in enormous quantities, make the auxiliary parking system installation effectiveness improve greatly.
Description of drawings
Fig. 1 is that the debugging template of the camera external parameter timing of prior art is laid synoptic diagram;
Fig. 2 is that the debugging template of the camera external parameter timing of the embodiment of the present application one is laid synoptic diagram;
Fig. 3 is the process flow diagram of the camera external parameter bearing calibration of the embodiment of the present application one;
Fig. 4 is the synoptic diagram that concerns between debugging template, camera, source images and the template image of the embodiment of the present application one;
Fig. 5 is the structural representation of the camera external parameter means for correcting of the embodiment of the present application one;
Fig. 6 lays synoptic diagram for the debugging template of the camera external parameter timing of application embodiment two;
Fig. 7 is the process flow diagram of the camera external parameter bearing calibration of the embodiment of the present application two;
Fig. 8 is the synoptic diagram that concerns between debugging template, camera, source images and the template image of the embodiment of the present application two.
Embodiment
In conjunction with the accompanying drawings the application is described in further detail below by embodiment.
Embodiment one:
The camera external parameter bearing calibration of present embodiment is mainly based on a kind of auxiliary parking system, it comprises two cameras, debugging template, a camera external parameter means for correcting, and output unit, wherein first camera 203 has reliable external parameter, in other words, first camera 203 has more accurate external parameter.As shown in Figure 2, before the correction, debugging template 201 is unfolded and is positioned among the figure in the zone 202, and zone 202 is zones that two cameras 203,204 all can detect, and debugging template 201 can adopt white flexible material or decoration that pattern etc. is arranged.Based on this, said method mainly comprises flow process as shown in Figure 3:
Step 301, obtain two cameras 203, two source images 401 that the debugging template 201 of 204 pairs of expansion is taken respectively, 403, particularly, first template image 402 that has debugging template 201 correspondences in first source images 401 that first camera 203 is taken, as shown in Figure 4, and second template image 404 of existence debugging template 201 correspondences in second source images 403 that second camera 204 is taken, because camera alignment error, make win template image 402 and the 404 meeting generation distortions of second template image, for example, it originally is circular debugging template, first template image 402 and second template image 404 will be twisted into the image of the similar ellipse in border, and be foursquare debugging template originally, first template image 402 and second template image 404 will be twisted into the image of similar rhombus in border or rectangle etc.;
Step 302, from first source images 401, obtain first template image 402, from second source images 403, obtain second template image 404, particularly, can pass through priori, get rid of the interference (video picture in image is disturbed as light shade, other objects, ground lines etc.) in the source images, obtain template image;
Step 303, respectively first template image 402 and second template image 404 are carried out match with the similar fitted shapes of debugging template 201 shapes, obtain the first fitted figure picture and the second fitted figure picture, particularly, because first template image 402 and second template image 404 are the set that are present in the pixel in first source images 401 and second source images 403 respectively, during match, can select corresponding fitted shapes that first template image 402 and second template image 404 are carried out match according to the shape of debugging template 201, a kind of embodiment is, artificial configuration and a corresponding fitted shapes of shape of debugging template 201, perhaps when presetting when debugging corresponding at least two preset shapes of template 201 shapes, from preset shapes, select one to carry out subsequent treatment at random as fitted shapes, for example, the circle that is shaped as when debugging template 201, can select fitted shapes so is that ellipse carries out match to first template image 402 and second template image 404, and the resulting first fitted figure picture and the second fitted figure picture are exactly oval; When the circle that is shaped as of debugging template 201, can select fitted shapes so is that rectangle or rhombus carry out match to first template image 402 and second template image 404, and it is exactly rectangle or rhombus that the resulting first fitted figure picture and second fitted figure look like; Match can be adopted image binaryzation, extract profile, and with the profile of Hough (Hough) conversion match template image, and then obtain the fitted figure picture;
Step 304, obtain the first packet size parameter and the second packet size parameter of the first fitted figure picture and the second fitted figure picture respectively, particularly, when fitted shapes is ellipse, the dimensional parameters of fitted figure picture can comprise centre coordinate and axial length etc., and axial length can comprise that minor axis is long long with major axis; When fitted shapes was rhombus, angle, centre coordinate and the center that the dimensional parameters of fitted figure picture can comprise the rhombus both sides was to the distance on rhombus limit etc.;
Step 305, by the first packet size parameter and the second packet size parameter determine the parameter error relevant with the external parameter of second camera 204 with, particularly, the external parameter of general camera is based on that world's coordinate system determines, this world coordinate system is an initial point with a certain end points of vehicle body, establish orthogonal x axle based on the right-handed helix rule, y axle and z axle, the external parameter of camera is corresponding with world coordinate system, it mainly comprises x axle rotation parameter, y axle rotation parameter, z axle rotation parameter, x axle translation parameters, y axle translation parameters and z axle translation parameters, i.e. three rotation parameters and three translation parameterss; And based on above-mentioned dimensional parameters can obtain the parameter error relevant with the external parameter of second camera 204 and, for example, when fitted shapes is ellipse, parameter error and can comprise two parts: first is OC square according to the first fitted figure picture of centre coordinate gained and the second fitted figure picture, and second portion is the quadratic sum of the difference of each axial length of the first fitted figure picture and the second fitted figure picture and preset standard radius; When fitted shapes is rhombus, parameter error and can similarly determining;
Step 306, external parameter with parameter error and correction second camera 204, particularly, because the external parameter of second camera 204 is relevant with the above-mentioned parameter sum of errors, can set up with parameter error so and be dependent variable, external parameter with second camera 204 is the function of independent variable, when changing the external parameter of second camera 204, according to above-mentioned steps 301-305 gained parameter error and also can respective change, reach pre-determined number up to parameter error with less than the number of times of a predetermined threshold or above-mentioned correction external parameter, this moment, the external parameter of gained second camera 204 just met the requirements substantially, each camera that need proofread and correct external parameter is all handled equally, and the captured final image of each camera just can be finished splicing.
Correspondingly, in the auxiliary parking system of present embodiment, camera external parameter means for correcting can comprise structure as shown in Figure 5:
Template image retrieval module 502, be used for obtaining first template image 402 of debugging template 201 correspondences, from second source images 403 that second camera 204 is taken, obtain second template image 404 of debugging template 201 correspondences from first source images 401 that first camera 203 is taken;
Adjusting module is used to proofread and correct the external parameter of second camera 204;
Control module, be used for whenever carrying out the correction of the external parameter of one time second camera 204, all control image collection module 501, template image retrieval module 502, fitting module 503, parameter calculating module 504 and error calculating module 505 are carried out alignment processing, make resulting parameter error and constantly diminish, reach pre-determined number up to the number of times of proofreading and correct external parameter, perhaps resulting parameter error and less than predetermined threshold, specifically can adopt gradient descent algorithm, simulated annealing, genetic algorithm, particle swarm optimization, the evolution algorithm scheduling algorithm is realized, mainly is to seek extreme point on the higher-dimension curved surface.
Splice and export and corresponding output unit is used for image that first camera 203 is taken and proofread and correct final image that back second camera 204 takes through external parameter, the formation panoramic picture supplies the driver to park used.
In embodiment one,, therefore, can realize the correction of second camera, 204 portion of external parameters basically, but can play the effect of correction equally owing to only carry out the correction of camera external parameter based on a template image of debugging template 201 correspondences.
Embodiment two:
The camera external parameter bearing calibration of present embodiment is mainly based on a kind of auxiliary parking system, it comprises four cameras, four debugging template, camera external parameter means for correctings, and output unit, wherein first camera 603, the 3rd camera 607 have reliable external parameter, in other words, first camera 603 and the 3rd camera 607 all have more accurate external parameter.As shown in Figure 6, before the correction, the first debugging template 601 is unfolded and is positioned among the figure in the first area 602, first area 602 is two cameras 603,604 zones that all can detect, the second debugging template 605 identical with the first debugging template 601 is unfolded and is positioned among the figure in the second area 606, second area 606 is two cameras 604,607 zones that all can detect, the 3rd debugging template 608 is unfolded and is positioned among the figure in the 3rd zone 609, the 3rd zone 609 is two cameras 607,610 zones that all can detect, the 4th debugging template 611 is unfolded and is positioned among the figure in the 4th zone 612, the 4th zone 612 is two cameras 610,603 zones that all can detect, the debugging template all adopts white flexible material, and same specification is the circle of fixed size.Based on this, said method mainly comprises flow process as shown in Figure 7, and this flow process is in order to proofread and correct the external parameter of second camera 604, proofreaies and correct the similar too processing of external parameter of other cameras certainly:
Step 701, obtain three cameras 603,604, three source images 801 that the first debugging template 601 of 607 pairs of expansion is taken respectively, 802,803, particularly, there are first template image 804 of the first debugging template, 601 correspondences and second template image 805 of the 4th debugging template 611 correspondences in first source images 801 that first camera 603 is taken, as shown in Figure 8, and the 3rd template image 806 and second that has the first debugging template, 601 correspondences in second source images 802 that second camera 604 is taken is debugged the 4th template image 807 of template 605 correspondences, and the 5th template image 808 and the 3rd that has the second debugging template, 605 correspondences in the 3rd source images 803 that the 3rd camera 607 is taken is debugged the 6th template image 809 of template 608 correspondences, because camera alignment error, make the template image 804 of winning, second template image 805, the 3rd template image 806, the 4th template image 807, the 5th template image 808 and the 6th template image 809 can produce distortion, originally be circular debugging template, first template image 804, second template image 805, the 3rd template image 806, the 4th template image 807, the 5th template image 808 and the 6th template image 809 will be twisted into the image of the similar ellipse in border;
Step 702 obtains first template image 804 from first source images 801, obtain the 3rd template image 806 and the 4th template image 807 from second source images 802, obtains the 5th template image 808 from the 3rd source images 803;
Step 705, by the first packet size parameter, the 3rd packet size parameter, the 4th packet size parameter and the 5th packet size parameter determine the parameter error relevant with the external parameter of second camera 604 with, particularly, the external parameter of general camera is based on that world's coordinate system determines, this world coordinate system is an initial point with a certain end points of vehicle body, establish orthogonal x axle based on the right-handed helix rule, y axle and z axle, the external parameter of camera is corresponding with world coordinate system, it mainly comprises x axle rotation parameter, y axle rotation parameter, z axle rotation parameter, x axle translation parameters, y axle translation parameters and z axle translation parameters, i.e. three rotation parameters and three translation parameterss; And can obtain two parameter errors relevant with the external parameter of second camera 604 based on above-mentioned parameter, first parameter error is according to centre coordinate (X
i, Y
i) first fitted figure picture of gained and OC square and OC square of sum E of the 4th fitted figure picture and the 5th fitted figure picture of the 3rd fitted figure picture
D, second parameter error is the quadratic sum E of the difference of the axial length of the 3rd fitted figure picture and the 4th fitted figure picture and preset standard radius
R, specifically be calculated as follows:
Wherein, A and A' represent the first fitted figure picture and the 3rd fitted figure picture respectively, and B and B' represent the 4th fitted figure picture and the 5th fitted figure picture respectively;
Wherein, L
StandardRepresent the preset standard radius, there is a fixed proportion k in its radius with the debugging template, then if debugging template radius is R, L so
StandardThen be kR;
Step 707 is carried out processing as step 701-706 to the external parameter of camera 610, and the final image of camera 603,604,607,610 spliced and exports, and forms panoramic picture and parks used for the driver.
Correspondingly, in the auxiliary parking system of present embodiment, camera external parameter means for correcting can comprise still structure as shown in Figure 5:
Template image retrieval module 502, be used for obtaining first template image 804 of the first debugging template, 601 correspondences from first source images 801 that first camera 603 is taken, from second source images 802 that second camera 604 is taken, obtain the 3rd template image 806 of the first debugging template, 601 correspondences and the 4th template image 807 of the second debugging template, 605 correspondences, from the 3rd source images 803 that the 3rd camera 607 is taken, obtain the 5th template image 808 of the second debugging template, 605 correspondences;
Adjusting module is used to proofread and correct the external parameter of second camera 604;
Control module, be used for whenever carrying out the correction of the external parameter of one time second camera 604, all control image collection module 501, template image retrieval module 502, fitting module 503, parameter calculating module 504 and error calculating module 505 are carried out alignment processing, make resulting parameter error and constantly diminish, reach pre-determined number up to the number of times of proofreading and correct external parameter, perhaps resulting parameter error and E are less than predetermined threshold, specifically can adopt gradient descent algorithm, simulated annealing, genetic algorithm, particle swarm optimization, the evolution algorithm scheduling algorithm is realized, mainly is to seek extreme point on the higher-dimension curved surface.
And corresponding output unit is used at second camera 604 after external parameter is proofreaied and correct, and the final image that each camera is taken splices and export, forms panoramic picture and supplies the driver to park used.
In embodiment two,, therefore, can realize the correction of whole external parameters of camera owing to carry out the correction of camera external parameter based on the template image of four debugging template correspondences.
Implement the application's camera external parameter bearing calibration, device and auxiliary parking system, the zone that template places at least two cameras all can detect will be debugged, wherein the part camera has reliable external parameter, a certain camera need carry out external parameter and proofread and correct, from the source images that each camera is taken, obtain the template image of same debugging template correspondence, and it is carried out match, obtain at least two fitted figure pictures, dimensional parameters according to each fitted figure picture, determine the parameter error of the fitted figure picture relevant with the camera external parameter, and proofread and correct the external parameter of above-mentioned a certain camera with parameter error, like this, only need make the debugging template launch to place the observable zone of camera, and setting has the camera of reliable external parameter, just can adopt said method to carry out the adjustment of camera external parameter, simplified the construction conditions of debugging template, and then improved the camera external parameter and proofreaied and correct efficient, when carrying out auxiliary parking system when installing in enormous quantities, only need to launch placement and debug template in the precalculated position, vehicle only needs to reach assigned address in the pipelining mode, can carry out the camera external parameter and proofread and correct in enormous quantities, make the auxiliary parking system installation effectiveness improve greatly.
Above content be in conjunction with concrete embodiment to further describing that the application did, can not assert that the application's concrete enforcement is confined to these explanations.For the application person of an ordinary skill in the technical field, under the prerequisite that does not break away from the application's design, can also make some simple deduction or replace.
Claims (10)
1. camera external parameter bearing calibration is characterized in that, comprising:
Acquisition has first source images and second source images that second camera that first camera of reliable external parameter and pending external parameter proofread and correct is taken respectively the debugging template of launching;
From described first source images, obtain first template image of debugging template correspondence, from described second source images, obtain second template image of debugging template correspondence;
Respectively first template image and second template image are carried out match, obtain the first fitted figure picture and the second fitted figure picture with the similar fitted shapes of described debugging shape of template;
Obtain the first packet size parameter and the second packet size parameter of the described first fitted figure picture and the second fitted figure picture respectively;
By the described first packet size parameter and the second packet size parameter determine the parameter error relevant with the external parameter of second camera with;
External parameter with described parameter error and correction second camera.
2. camera external parameter bearing calibration is characterized in that, comprising:
Second source images that first source images that first camera that acquisition has a reliable external parameter is taken the first debugging template of launching, second camera that pending external parameter is proofreaied and correct are taken the described first debugging template launched and the second debugging template identical with the first debugging template, and have three source images of the 3rd camera of reliable external parameter to the described second debugging template shooting;
From described first source images, obtain first template image of the first debugging template correspondence, from described second source images, obtain second template image of the first debugging template correspondence and the 3rd template image of the second debugging template correspondence, from described the 3rd source images, obtain the 4th template image of the second debugging template correspondence;
Respectively first template image, second template image, the 3rd template image and the 4th template image are carried out match, obtain the first fitted figure picture, the second fitted figure picture, the 3rd fitted figure picture and the 4th fitted figure picture with the similar fitted shapes of the described first debugging shape of template;
Obtain the first packet size parameter, the second packet size parameter, the 3rd packet size parameter and the 4th packet size parameter of the described first fitted figure picture, the second fitted figure picture, the 3rd fitted figure picture and the 4th fitted figure picture respectively;
By the described first packet size parameter, the second packet size parameter, the 3rd packet size parameter and the 4th packet size parameter determine the parameter error relevant with the external parameter of second camera and;
External parameter with described parameter error and correction second camera.
3. method as claimed in claim 2 is characterized in that, when the described first debugging shape of template and the second debugging shape of template when be circular, described fitted shapes is an ellipse; Described first group of parameter, second group of parameter, the 3rd group of parameter and the 4th group of parameter comprise the centre coordinate of the first fitted figure picture, the second fitted figure picture, the 3rd fitted figure picture and the 4th fitted figure picture respectively, and the axial length of the described first fitted figure picture, the second fitted figure picture, the 3rd fitted figure picture and the 4th fitted figure picture; Described parameter error and comprise that first parameter error and second parameter error, described first parameter error be foundation first fitted figure picture of described centre coordinate gained and OC square and OC square of sum of the 3rd fitted figure picture and the 4th fitted figure picture of the second fitted figure picture; Described second parameter error is the quadratic sum of the difference of the axial length of described second fitted figure picture and the 3rd fitted figure picture and preset standard radius.
4. method as claimed in claim 3 is characterized in that, repeats described correction, reaches pre-determined number up to the number of times of described correction, the parameter error after the perhaps described correction and less than predetermined threshold.
5. method as claimed in claim 4 is characterized in that, the final image of first camera, second camera and the 3rd camera of described processing gained is spliced.
6. a camera external parameter means for correcting is characterized in that, comprising:
Image collection module is used to obtain to have first camera of reliable external parameter and second camera of pending external parameter correction is debugged first source images and second source images that template is taken respectively to first of expansion;
The template image retrieval module is used for obtaining to debug first template image of template correspondence from described first source images, obtains second template image of debugging template correspondence from described second source images;
Fitting module is used for obtaining the first fitted figure picture and the second fitted figure picture respectively first template image and second template image are carried out match with the similar fitted shapes of described debugging shape of template;
Parameter calculating module is used for obtaining respectively the first packet size parameter and the second packet size parameter of the described first fitted figure picture and the second fitted figure picture;
Error calculating module, be used for by the described first packet size parameter and the second packet size parameter determine the parameter error relevant with the external parameter of second camera with;
Correction module is used for the external parameter with parameter error and correction second camera.
7. device as claimed in claim 6 is characterized in that, described correction module comprises:
Adjusting module is used to proofread and correct the external parameter of described second camera;
Control module, be used for carrying out once described correction whenever, control described image collection module, template image retrieval module, fitting module, parameter calculating module and error calculating module and carry out alignment processing, number of times up to described correction reaches pre-determined number, the parameter error after the perhaps described correction and less than predetermined threshold.
8. a camera external parameter means for correcting is characterized in that, comprising:
Image collection module, be used to have second source images that first source images that first camera of reliable external parameter takes the first debugging template of launching, second camera that pending external parameter is proofreaied and correct are taken the described first debugging template launched and the second debugging template identical with the first debugging template, and have three source images of the 3rd camera of reliable external parameter the described second debugging template shooting;
The template image retrieval module, be used for obtaining first template image of the first debugging template correspondence from described first source images, from described second source images, obtain second template image of the first debugging template correspondence and the 3rd template image of the second debugging template correspondence, from described the 3rd source images, obtain the 4th template image of the second debugging template correspondence;
Fitting module, be used for obtaining the first fitted figure picture, the second fitted figure picture, the 3rd fitted figure picture and the 4th fitted figure picture respectively first template image, second template image, the 3rd template image and the 4th template image are carried out match with the similar fitted shapes of the described first debugging shape of template;
Parameter calculating module is used for obtaining respectively the first packet size parameter, the second packet size parameter, the 3rd packet size parameter and the 4th packet size parameter of the described first fitted figure picture, the second fitted figure picture, the 3rd fitted figure picture and the 4th fitted figure picture;
Error calculating module, be used for by the described first packet size parameter, the second packet size parameter, the 3rd packet size parameter and the 4th packet size parameter determine the parameter error relevant with the external parameter of second camera and;
Correction module is used for the external parameter with described parameter error and correction second camera.
9. device as claimed in claim 8 is characterized in that, described correction module comprises:
Adjusting module is used to proofread and correct the external parameter of putting in order described second camera;
Control module, be used for carrying out once described correction whenever, control described image collection module, template image retrieval module, fitting module, parameter calculating module and error calculating module and carry out alignment processing, number of times up to described correction reaches pre-determined number, the parameter error after the perhaps described correction and less than predetermined threshold.
10. an auxiliary parking system comprises at least two cameras, it is characterized in that, described system also comprises:
As each described camera external parameter means for correcting among the claim 6-9, and,
Output unit is used for described second camera being carried out after external parameter proofreaies and correct, and the final image that each camera is taken splices and exports.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310092299.3A CN103226827B (en) | 2013-03-21 | 2013-03-21 | Camera external parameter correction method, device and auxiliary parking system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310092299.3A CN103226827B (en) | 2013-03-21 | 2013-03-21 | Camera external parameter correction method, device and auxiliary parking system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103226827A true CN103226827A (en) | 2013-07-31 |
| CN103226827B CN103226827B (en) | 2016-04-27 |
Family
ID=48837262
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310092299.3A Active CN103226827B (en) | 2013-03-21 | 2013-03-21 | Camera external parameter correction method, device and auxiliary parking system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103226827B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106709956A (en) * | 2016-12-30 | 2017-05-24 | 广州汽车集团股份有限公司 | Remote calibration method and system of panorama image system |
| CN107341766A (en) * | 2017-05-25 | 2017-11-10 | 深圳市汉华安道科技有限责任公司 | A kind of image automatic debugging system of panoramic parking assist system, method and apparatus |
| CN107660297A (en) * | 2015-05-26 | 2018-02-02 | 克朗设备公司 | The system and method that image capture apparatus for materials handling vehicle is calibrated |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101093581A (en) * | 2006-06-23 | 2007-12-26 | 佳能株式会社 | Information processing method and apparatus for calculating information regarding measurement target on the basis of captured images |
| CN101425181A (en) * | 2008-12-15 | 2009-05-06 | 浙江大学 | Panoramic view vision auxiliary parking system demarcating method |
| US20090207045A1 (en) * | 2008-02-14 | 2009-08-20 | Mando Corporation | Method and apparatus for detecting target parking position by using two reference points, and parking assist system using the same |
| CN102045546A (en) * | 2010-12-15 | 2011-05-04 | 广州致远电子有限公司 | Panoramic parking assist system |
| CN102298771A (en) * | 2011-08-16 | 2011-12-28 | 淮安盈科伟力科技有限公司 | Fish-eye image rapid correction method of panoramic parking auxiliary system |
-
2013
- 2013-03-21 CN CN201310092299.3A patent/CN103226827B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101093581A (en) * | 2006-06-23 | 2007-12-26 | 佳能株式会社 | Information processing method and apparatus for calculating information regarding measurement target on the basis of captured images |
| US20090207045A1 (en) * | 2008-02-14 | 2009-08-20 | Mando Corporation | Method and apparatus for detecting target parking position by using two reference points, and parking assist system using the same |
| CN101425181A (en) * | 2008-12-15 | 2009-05-06 | 浙江大学 | Panoramic view vision auxiliary parking system demarcating method |
| CN102045546A (en) * | 2010-12-15 | 2011-05-04 | 广州致远电子有限公司 | Panoramic parking assist system |
| CN102298771A (en) * | 2011-08-16 | 2011-12-28 | 淮安盈科伟力科技有限公司 | Fish-eye image rapid correction method of panoramic parking auxiliary system |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107660297A (en) * | 2015-05-26 | 2018-02-02 | 克朗设备公司 | The system and method that image capture apparatus for materials handling vehicle is calibrated |
| CN107660297B (en) * | 2015-05-26 | 2021-12-10 | 克朗设备公司 | System and method for image capture device calibration of a materials handling vehicle |
| CN106709956A (en) * | 2016-12-30 | 2017-05-24 | 广州汽车集团股份有限公司 | Remote calibration method and system of panorama image system |
| CN106709956B (en) * | 2016-12-30 | 2020-05-15 | 广州汽车集团股份有限公司 | Remote calibration method and system of panoramic image system |
| CN107341766A (en) * | 2017-05-25 | 2017-11-10 | 深圳市汉华安道科技有限责任公司 | A kind of image automatic debugging system of panoramic parking assist system, method and apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103226827B (en) | 2016-04-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105844624B (en) | Combined optimization method and device in dynamic calibration system, dynamic calibration system | |
| CN105354796B (en) | Image processing method and system for auxiliary of driving a vehicle | |
| CN106373091A (en) | Automatic panorama parking aerial view image splicing method, system and vehicle | |
| CN103177439A (en) | Automatically calibration method based on black and white grid corner matching | |
| CN102663734A (en) | Fish eye lens calibration and fish eye image distortion correction method | |
| CN103226827A (en) | Camera external parameter correction method and device, and assistant parking system | |
| CN104732482A (en) | Multi-resolution image stitching method based on control points | |
| CN104820973B (en) | The method for correcting image of distortion curve radian detection template | |
| CN106485756B (en) | A kind of parking system camera calibration method | |
| CN101276415A (en) | Apparatus and method for realizing multi-resolutions image acquisition with multi-focusing video camera | |
| CN104657982A (en) | Calibration method for projector | |
| CN109087251A (en) | A kind of vehicle-mounted panoramic image display method and system | |
| CN105608706B (en) | A kind of polarization vision sensor structure design and geometric calibration method | |
| CN103996173A (en) | Fisheye image correction method based on changed long axis ellipse fitting | |
| CN107993264A (en) | A kind of automobile looks around the scaling method of panorama | |
| CN104298887A (en) | Relative radiation calibration method of multichip linear CCD (charge coupled device) camera | |
| CN103854272A (en) | Panorama parking system automatic point matching method | |
| CN110850109B (en) | Method for measuring vehicle speed based on fuzzy image | |
| CN107146255A (en) | Panoramic picture error calibration method and device | |
| CN106600549A (en) | Method and device for correcting fisheye image | |
| CN105069761A (en) | Low-calculation cylindrical surface panoramagram realization method and system | |
| CN206317810U (en) | A kind of vehicle travels 360 degree of panorama driving scaling boards | |
| CN115239820A (en) | Split type flying vehicle aerial view real-time splicing and parking space detection method | |
| CN105741296A (en) | Auxiliary calibration method of 360-degre all-visual-angle aerial view panorama travelling crane | |
| CN102694963A (en) | Method for acquiring shadeless target image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20180408 Address after: 518000 Guangdong city of Shenzhen province Nanshan District Nanshan Street Bay Road No. 2076 building 7 building 79049 hi tech group Patentee after: Shenzhen Bowei Yuanjing Technology Co. Ltd. Address before: 518055 Guangdong city of Shenzhen province Nanshan District Taoyuan University City Street Lishan Pioneering Park Room 804 Patentee before: ShenZhen Safdao Technology Corporation Limited |
|
| TR01 | Transfer of patent right |